When working with large datasets on Hugging Face, downloading in JSON format can be cumbersome due to the large size of the files. Fortunately, some datasets provide automatically converted Parquet versions, which are much smaller and optimized for efficient data storage and access.
In this example, we demonstrate how to download only the Parquet files instead of the entire dataset in JSON.
Dataset URL: ScaleQuest-Math
| param([Parameter(Mandatory)]$key, [Parameter(Mandatory)]$value, $file='.\i18n.json') | |
| if ($value -eq $null) { | |
| $value = read-host -Prompt "Please enter a value" | |
| } | |
| function Format-Json([Parameter(Mandatory, ValueFromPipeline)][String] $json) { | |
| $indent = 0; | |
| ($json -Split "`n" | % { | |
| if ($_ -match '[\}\]]\s*,?\s*$') { |
| interface Presentation { | |
| defaultRequest: PresentationRequest; | |
| receiver: PresentationReceiver; | |
| } | |
| interface PresentationReceiver { | |
| connectionList: Promise<PresentationConnectionList>; | |
| } | |
| interface PresentationConnection { | |
| binaryType: ArrayBuffer | Blob; |
| interface DocumentWithFullscreen extends HTMLDocument { | |
| mozFullScreenElement?: Element; | |
| msFullscreenElement?: Element; | |
| webkitFullscreenElement?: Element; | |
| msExitFullscreen?: () => void; | |
| mozCancelFullScreen?: () => void; | |
| webkitExitFullscreen?: () => void; | |
| } | |
| export function isFullScreen(): boolean { |
| import { Observable } from 'rxjs'; | |
| import fetch, { RequestInit, Request, Response } from 'node-fetch'; | |
| import AbortController from 'abort-controller'; | |
| export type RequestInit = RequestInit; | |
| export function fromFetch(input: string | Request, init?: RequestInit): Observable<Response> { | |
| return new Observable<Response>(subscriber => { | |
| const controller = new AbortController(); | |
| const signal = controller.signal; |
| import { ipcMain, BrowserWindow, Event } from 'electron' | |
| const getResponseChannels = (channel:string) => ({ | |
| sendChannel: `%app-send-channel-${channel}`, | |
| dataChannel: `%app-response-data-channel-${channel}`, | |
| errorChannel: `%app-response-error-channel-${channel}` | |
| }) | |
| const getRendererResponseChannels = (windowId: number, channel: string) => ({ | |
| sendChannel: `%app-send-channel-${windowId}-${channel}`, |
| robocopy . E:\backup\GIT\. /IS /S /XD node_modules |
| { | |
| "language": "en", | |
| "timezone": "UTC", | |
| "agentName": "SaraCSML", | |
| "useWebhook": false, | |
| "description": "Sara is support chatbot for update management.", | |
| "fallbackResponses": [ | |
| "Sorry can you rephrase that?", | |
| "I'm still learning to speak with humans. What you mean?" | |
| ], |
| #!/bin/bash | |
| docker volume create $docker_volume | |
| docker-machine ssh default -- "sh -c 'sudo mount -o uid=1000,gid=1000 -t vboxsf $docker_volume $(docker inspect $docker_volume -f {{.Mountpoint}})'" |
| http_proxy=http://194.138.0.3:9400 | |
| https_proxy=http://194.138.0.3:9400 |